Closing the gap on lower cost air quality monitoring: machine learning calibration models to improve low-cost sensor performance

Low-cost sensing strategies hold the promise of denser air quality monitoring networks, which could significantly improve our understanding of personal air pollution exposure. Additionally, low-cost air quality sensors could be deployed to areas where limited monitoring exists. However, low-cost sensors are frequently sensitive to environmental conditions and pollutant cross-sensitivities, which have historically been poorly addressed by laboratory calibrations, limiting their utility for monitoring. In this study, we investigated different calibration models for the Real-time Affordable Multi-Pollutant (RAMP) sensor package, which measures CO, NO 2 , O 3 , and CO 2 . We explored three methods: 1) laboratory univariate linear regression, 2) empirical multivariate linear regression and 3) machine-learning based calibration models using random forests (RF). Calibration models were developed for 19 RAMP monitors using training and testing windows spanning August 2016 through February 2017 in Pittsburgh, PA. The random forest models matched (CO) or significantly outperformed (NO 2 , CO 2 , O 3 ) the other calibration models, and their accuracy and precision was robust over time for testing windows of up to 16 weeks. Following calibration, average mean absolute error on the testing dataset from the random forest models was 38 ppb for CO (14 % relative error), 10 ppm for CO 2 (2 % relative error), 3.5 ppb for NO 2 (29 % relative error) and 3.4 ppb for O 3 (15 % relative error), and Pearson r versus the reference monitors exceeded 0.8 for most units. Model performance is explored in detail, including a quantification of model variable importance, accuracy across different concentration ranges, and performance in a range of monitoring contexts including the National Ambient Air Quality Standards (NAAQS), and the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. A key strength of the RF approach is that it accounts for pollutant cross sensitivities. This highlights the importance of developing multipollutant sensor packages (as opposed to single pollutant monitors); we determined this is especially critical for NO 2 and CO 2 . The evaluation reveals that only the RF-calibrated sensors meet the US EPA Air Sensors Guidebook recommendations of minimum data quality for personal exposure measurement. We also demonstrate that the RF model calibrated sensors could detect differences in NO 2 concentrations between a near-road site and a suburban site less than 1.5 km away. From this study, we conclude that combining RF models with the RAMP monitors appears to be a very promising approach to address the poor performance that has plagued low cost air quality sensors.

[1]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[2]  Jonathan I Levy,et al.  Factors influencing the spatial extent of mobile source air pollution impacts: a meta-analysis , 2007, BMC public health.

[3]  Michael Brauer,et al.  Within-urban variability in ambient air pollution: Comparison of estimation methods , 2008 .

[4]  J. Kindle,et al.  Summary diagrams for coupled hydrodynamic-ecosystem model skill assessment , 2009 .

[5]  C. N. Hewitt,et al.  Effectiveness of green infrastructure for improvement of air quality in urban street canyons. , 2012, Environmental science & technology.

[6]  Juana Maria Delgado-Saborit,et al.  Use of real-time sensors to characterise human exposures to combustion related pollutants. , 2012, Journal of environmental monitoring : JEM.

[7]  E. Snyder,et al.  The changing paradigm of air pollution monitoring. , 2013, Environmental science & technology.

[8]  J. Salmond,et al.  Validation of low-cost ozone measurement instruments suitable for use in an air-quality monitoring network , 2013 .

[9]  S. Laurent,et al.  Protocol of evaluation and calibration of low-cost gas sensors for the monitoring of air pollution , 2013 .

[10]  Gb Stewart,et al.  The use of electrochemical sensors for monitoring urban air quality in low-cost, high-density networks , 2013 .

[11]  A. Robinson,et al.  Characterizing the spatial variation of air pollutants and the contributions of high emitting vehicles in Pittsburgh, PA. , 2014, Environmental science & technology.

[12]  L. Shang,et al.  The next generation of low-cost personal air quality sensors for quantitative exposure monitoring , 2014 .

[13]  David E Williams,et al.  High density ozone monitoring using gas sensitive semi-conductor sensors in the Lower Fraser Valley, British Columbia. , 2014, Environmental science & technology.

[14]  U. Lerner,et al.  On the feasibility of measuring urban air pollution by wireless distributed sensor networks. , 2015, The Science of the total environment.

[15]  Max Kuhn,et al.  caret: Classification and Regression Training , 2015 .

[16]  Michael Hannigan,et al.  Quantification Method for Electrolytic Sensors in Long-Term Monitoring of Ambient Air Quality , 2015, Sensors.

[17]  R. Piedrahita,et al.  Approach for quantification of metal oxide type semiconductor gas sensors used for ambient air quality monitoring , 2015 .

[18]  L. Spinelle,et al.  Sensors and Actuators B: Chemical Field calibration of a cluster of low-cost available sensors for air quality monitoring. Part A: Ozone and nitrogen dioxide (cid:2) , 2022 .

[19]  A. Lewis,et al.  Validate personal air-pollution sensors , 2016, Nature.

[20]  Michael L. Wheeler,et al.  Performance Evaluation and Community Application of Low-Cost Sensors for Ozone and Nitrogen Dioxide , 2016, Sensors.

[21]  S. De Vito,et al.  Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems , 2016 .

[22]  Laurent Francis,et al.  Assessment of air quality microsensors versus reference methods: The EuNetAir joint exercise , 2016 .

[23]  G. Hagler,et al.  Community Air Sensor Network (CAIRSENSE) project: evaluation of low-cost sensor performance in a suburban environment in the southeastern United States. , 2016, Atmospheric measurement techniques.

[24]  D. Worsnop,et al.  Use of electrochemical sensors for measurement of air pollution: correcting interference response and validating measurements , 2017 .

[25]  Alastair C. Lewis,et al.  Electrochemical ozone sensors: A miniaturised alternative for ozone measurements in laboratory experiments and air-quality monitoring , 2017 .

[26]  Grant R. McKercher,et al.  Characteristics and applications of small, portable gaseous air pollution monitors. , 2017, Environmental pollution.

[27]  L. Spinelle,et al.  Field calibration of a cluster of low-cost commercially available sensors for air quality monitoring. Part B: NO, CO and CO2 , 2017 .

[28]  Alena Bartonova,et al.  Can commercial low-cost sensor platforms contribute to air quality monitoring and exposure estimates? , 2017, Environment international.